{"slug": "memory-as-action-autonomous-context-curation-for-long-horizon-agentic-tasks", "title": "Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks", "summary": "Researchers have developed Memory-as-Action (MemAct), a framework that treats working memory management as learnable policy actions for large language models, enabling joint optimization of information retention and task performance through end-to-end reinforcement learning. The MemAct-RL-14B model matched the accuracy of models 16 times larger while reducing average context length by 51%, addressing attention dilution in long-horizon tasks. The framework introduces Dynamic Context Policy Optimization to restore training efficiency without compromising reasoning integrity, with learned strategies that adapt to model capabilities and generalize across task complexities.", "body_md": "# Computer Science > Artificial Intelligence\n\n[Submitted on 14 Oct 2025 (\n\n[v1](https://arxiv.org/abs/2510.12635v1)), last revised 7 May 2026 (this version, v3)]# Title:Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks\n\n[View PDF](/pdf/2510.12635)\n\n[HTML (experimental)](https://arxiv.org/html/2510.12635v3)\n\nAbstract:Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness of the agent's reasoning state, leading to suboptimal decisions. We propose Memory-as-Action (MemAct), a framework that treats working memory management as learnable policy actions. By formulating context management as in-place editing operations (deletion, insertion), MemAct enables joint optimization of information retention and task performance through end-to-end reinforcement learning. To address the computational challenges of dynamic context updates, we introduce Dynamic Context Policy Optimization, which restores training efficiency without compromising reasoning integrity. Experiments show that MemAct-RL-14B matches the accuracy of models $16\\times$ larger while reducing average context length by 51\\%, with learned strategies that adapt to model capabilities and generalize across task complexities.\n\n## Submission history\n\nFrom: Yuxiang Zhang [[view email](/show-email/46b9f528/2510.12635)]\n\n**Tue, 14 Oct 2025 15:29:57 UTC (327 KB)**\n\n[[v1]](/abs/2510.12635v1)**Sat, 10 Jan 2026 01:44:56 UTC (374 KB)**\n\n[[v2]](/abs/2510.12635v2)**[v3]** Thu, 7 May 2026 13:18:53 UTC (371 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/memory-as-action-autonomous-context-curation-for-long-horizon-agentic-tasks", "canonical_source": "https://arxiv.org/abs/2510.12635", "published_at": "2026-05-31 07:27:28+00:00", "updated_at": "2026-05-31 07:44:51.384979+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "machine-learning", "ai-agents", "natural-language-processing"], "entities": ["Memory-as-Action", "MemAct", "Dynamic Context Policy Optimization", "Yuxiang Zhang"], "alternates": {"html": "https://wpnews.pro/news/memory-as-action-autonomous-context-curation-for-long-horizon-agentic-tasks", "markdown": "https://wpnews.pro/news/memory-as-action-autonomous-context-curation-for-long-horizon-agentic-tasks.md", "text": "https://wpnews.pro/news/memory-as-action-autonomous-context-curation-for-long-horizon-agentic-tasks.txt", "jsonld": "https://wpnews.pro/news/memory-as-action-autonomous-context-curation-for-long-horizon-agentic-tasks.jsonld"}}